A method for solving discrepancy between optical flow field and motion field due to self-similar characteristics

An optical flow field and self-similar technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as inconsistency and affecting the accuracy of optical flow tracking methods

Inactive Publication Date: 2019-02-15
深圳市艾为智能有限公司
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since optical flow tracking is based on the premise of illumination invariance and regional consistency assumptions, when there are repeated textures in the image, the self-similar features of the texture often cause the tracking result of the optical flow field to be inconsistent with the motion field of the actual object, thus affecting Accuracy of optical flow tracking method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method for solving discrepancy between optical flow field and motion field due to self-similar characteristics
  • A method for solving discrepancy between optical flow field and motion field due to self-similar characteristics
  • A method for solving discrepancy between optical flow field and motion field due to self-similar characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0098] The technical solution of the present invention will be further described below in conjunction with the drawings and specific embodiments.

[0099] See Figure 1-Figure 7 , A method for solving the discrepancy between the optical flow field and the sports field caused by self-similar features, mainly includes the following steps:

[0100] Step 1: Obtain a single-channel video stream and a single-channel grayscale image.

[0101] Step 2: Perform image pyramid processing on the image to create a K-layer pyramid.

[0102] Step 3: Divide the first layer of the original image pyramid into Number=Col×Row detection areas, and detect one feature point in each detection area, and at most Number feature points can be detected. The characteristic point is represented by P.

[0103] Step 4: Apply formulas (3)~(6) on the original image to calculate the virtual displacement sequence V, and use formula (1) to obtain the virtual displacement image sequence I v , Contains m virtual displacement...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

In order to improve the consistency of an optical flow field and a motion field due to the self-similar characteristicsj, a method for detecting the inconsistency between optical flow field and motionfield generated by the self-similar feature includes the steps of obtaining single channel video stream and single channel gray scale image, carrying out the image pyramid processing on the image tomake the pyramid of K layers; dividing the first pyramid layer of the original image into detection regions, detecting a feature point in each detection region, calculating a virtual displacement sequence V on the original image, and obtaining a virtual displacement image sequence IV, comprising m virtual displacement images; carrying out image pyramid processing on each virtual displacement imageto obtain m K-layer virtual displacement pyramids, wherein each V (i) corresponds to one virtual displacement pyramid; finally, obtaining the optical flow field by traditional optical flow tracking using the feature points after virtual displacement filtering.

Description

Technical field [0001] The present invention relates to the detection technology of optical flow field, in particular to a method for solving the discrepancy between the optical flow field caused by self-similar features and the actual sports field. Background technique [0002] Computational image optical flow field is the basic research content of computer motion vision and an important tool for motion analysis and understanding. It plays an important role in motion detection, motion estimation, motion tracking, motion recognition and other applications. Since optical flow tracking is based on the assumption of illumination invariance and regional consistency, when there are repeated textures in the image, the self-similar characteristics of the texture will often cause the tracking results of the optical flow field to be inconsistent with the motion field of the actual object, thereby affecting The accuracy of the optical flow tracking method. Summary of the invention [0003]...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/246
CPCG06T7/246G06T2207/20016
Inventor 陈一君徐洪徐琳
Owner 深圳市艾为智能有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap